tcp: fix retransmission in repair mode

Currently if a socket was repaired with a few packet in a write queue,
a kernel bug may be triggered:

kernel BUG at net/ipv4/tcp_output.c:2330!
RIP: 0010:[<ffffffff8155784f>] tcp_retransmit_skb+0x5ff/0x610

According to the initial realization v3.4-rc2-963-gc0e88ff,
all skb-s should look like already posted. This patch fixes code
according with this sentence.

Here are three points, which were not done in the initial patch:
1. A tcp send head should not be changed
2. Initialize TSO state of a skb
3. Reset the retransmission time

This patch moves logic from tcp_sendmsg to tcp_write_xmit. A packet
passes the ussual way, but isn't sent to network. This patch solves
all described problems and handles tcp_sendpages.

Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: James Morris <jmorris@namei.org>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Patrick McHardy <kaber@trash.net>
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 197c000..083092e 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1212,7 +1212,7 @@ new_segment:
 wait_for_sndbuf:
                        set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
-                       if (copied && likely(!tp->repair))
+                       if (copied)
                                tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
 
                        if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
@@ -1223,7 +1223,7 @@ wait_for_memory:
        }
 
 out:
-       if (copied && likely(!tp->repair))
+       if (copied)
                tcp_push(sk, flags, mss_now, tp->nonagle);
        release_sock(sk);
        return copied + copied_syn;

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index cfe6ffe..2798706 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1986,6 +1986,9 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
                tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
                BUG_ON(!tso_segs);
 
+               if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE)
+                       goto repair; /* Skip network transmission */
+
                cwnd_quota = tcp_cwnd_test(tp, skb);
                if (!cwnd_quota)
                        break;
@@ -2026,6 +2029,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
                if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
                        break;
 
+repair:
                /* Advance the send_head.  This one is sent out.
                 * This call will increment packets_out.
                 */